meeting-insights-analyzer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs the agent to extract and include verbatim quotes and identifiers from local transcripts (e.g., "Actual quote from transcript"), so if those files contain API keys, passwords, or other secrets the LLM would reproduce them in its output, creating an exfiltration risk.